Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 574 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0002

Data Index: 660483 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1203525 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0448. Min Act: -0.0002

Data Index: 287229 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1146807 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0439. Min Act: -0.0002

Data Index: 633923 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0415. Min Act: -0.0002

Data Index: 322257 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0414. Min Act: -0.0002

Data Index: 154737 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0419. Min Act: -0.0002

Data Index: 783575 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1118568 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0407. Min Act: -0.0002

Data Index: 5690 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1249517 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0404. Min Act: -0.0002

Data Index: 928246 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1169044 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0394. Min Act: -0.0002

Data Index: 733383 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1135697 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0392. Min Act: -0.0002

Data Index: 592378 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0381. Min Act: -0.0002

Data Index: 946381 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0384. Min Act: -0.0002

Data Index: 552633 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0395. Min Act: -0.0002

Data Index: 762263 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0362. Min Act: -0.0002

Data Index: 238993 (C4 (Web Text))

Max Activating Token Index: 961